<div class="csl-bib-body">
<div class="csl-entry">Giunchiglia, E., Stoian, M. C., Khan, S., Cuzzolin, F., & Lukasiewicz, T. (2023). ROAD-R: the autonomous driving dataset with logical requirements. <i>Machine Learning</i>, <i>112</i>, 3261–3291. https://doi.org/10.1007/s10994-023-06322-z</div>
</div>
-
dc.identifier.issn
0885-6125
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/191509
-
dc.description.abstract
Neural networks have proven to be very powerful at computer vision tasks. However, they often exhibit unexpected behaviors, acting against background knowledge about the problem at hand. This calls for models (i) able to learn from requirements expressing such background knowledge, and (ii) guaranteed to be compliant with the requirements themselves. Unfortunately, the development of such models is hampered by the lack of real-world datasets equipped with formally specified requirements. In this paper, we introduce the ROad event Awareness Dataset with logical Requirements (ROAD-R), the first publicly available dataset for autonomous driving with requirements expressed as logical constraints. Given ROAD-R, we show that current state-of-the-art models often violate its logical constraints, and that it is possible to exploit them to create models that (i) have a better performance, and (ii) are guaranteed to be compliant with the requirements themselves.
en
dc.language.iso
en
-
dc.publisher
SPRINGER
-
dc.relation.ispartof
Machine Learning
-
dc.subject
Deep learning
en
dc.subject
Logical constraints
en
dc.subject
Requirements
en
dc.subject
Safety
en
dc.title
ROAD-R: the autonomous driving dataset with logical requirements